Hyperspectral imaging (HSI) is an emerging imaging modality for medical applications. HSI acquires two dimensional images at various wavelengths. The combination of both spectral and spatial information provides quantitative information for cancer detection and diagnosis. This paper proposes using superpixels, principal component analysis (PCA), and support vector machine (SVM) to distinguish regions of tumor from healthy tissue. The classification method uses 2 principal components decomposed from hyperspectral images and obtains an average sensitivity of 93% and an average specificity of 85% for 11 mice. The hyperspectral imaging technology and classification method can have various applications in cancer research and management.
Dual energy digital mammography has been used to suppress specific breast tissue, primarily for the purpose of iodine
contrast-enhanced imaging. Another application of dual energy digital mammography is to estimate breast density, as
defined by the fraction of glandular tissue, by suppressing adipose tissue. Adipose equivalent phantoms were used to
derive the weighting factor for dual energy subtraction at 2, 4, 6, and 8 cm thickness. For each thickness besides 8 cm,
measurements were taken over a range of densities (0, 50, and 100%) and used for calibration measurements to model a density map. Once the density map was verified with uniform slabs, the density map was evaluated with 50/50 CIRS 020 phantom at 2, 4, and 6 cm thickness and demonstrated the feasibility of using dual energy subtraction to estimate breast density on complex phantoms.